Related papers: CHoE: Cross-Domain Heterogeneous Graph Prompt Lear…

Foundation models have achieved great success in natural language processing (NLP) and computer vision (CV). Their success largely stems from the ability to integrate multi-domain knowledge in pre-training and transfer it to target domains.…

Real-world heterogeneous graphs are inherently noisy and usually not in the optimal graph structures for downstream tasks, which often adversely affects the performance of GRL models in downstream tasks. Although Graph Structure Learning…

The sparse Mixture-of-Experts (MoE) architecture of large language models (LLMs) confronts an inherent issue of load imbalance arising from the simplistic linear router strategy, which ultimately causes the instability and inefficient…

Graph neural networks stand as the predominant technique for graph representation learning owing to their strong expressive power, yet the performance highly depends on the availability of high-quality labels in an end-to-end manner. Thus…

Most existing training systems focus on a single region. In contrast, we envision that cross-region training offers more flexible GPU resource allocation and yields significant potential. However, the hierarchical cluster topology and…

Heterogeneous graphs are pervasive in practical scenarios, where each graph consists of multiple types of nodes and edges. Representation learning on heterogeneous graphs aims to obtain low-dimensional node representations that could…

Due to domain shifts, machine learning systems typically struggle to generalize well to new domains that differ from those of training data, which is what domain generalization (DG) aims to address. Although a variety of DG methods have…

Contrastive Learning (CL)-based recommender systems have gained prominence in the context of Heterogeneous Graph (HG) due to their capacity to enhance the consistency of representations across different views. However, existing frameworks…

Recommender systems are frequently challenged by the data sparsity problem. One approach to mitigate this issue is through cross-domain recommendation techniques. In a cross-domain context, sharing knowledge between domains can enhance the…

Graph-structured data is ubiquitous in the world which models complex relationships between objects, enabling various Web applications. Daily influxes of unlabeled graph data on the Web offer immense potential for these applications. Graph…

A common practice in heterogeneous graph neural networks (HGNNs) is to condition parameters on node/edge types, assuming types reflect semantic roles. However, this can cause overreliance on surface-level labels and impede cross-type…

Graph neural networks (GNNs) have found extensive applications in learning from graph data. However, real-world graphs often possess diverse structures and comprise nodes and edges of varying types. To bolster the generalization capacity of…

Achieving both accurate and consistent predictive performance across spatial nodes is crucial for ensuring the validity and reliability of outcomes in fair spatial-temporal forecasting tasks. However, existing training methods treat…

Graph neural networks (GNNs) have been widely used in deep learning on graphs. They can learn effective node representations that achieve superior performances in graph analysis tasks such as node classification and node clustering.…

Heterogeneous graph neural network (HGNN) is a very popular technique for the modeling and analysis of heterogeneous graphs. Most existing HGNN-based approaches are supervised or semi-supervised learning methods requiring graphs to be…

Prompt-based methods have recently gained prominence in Continual Learning (CL) due to their strong performance and memory efficiency. A prevalent strategy in this paradigm assigns a dedicated subset of prompts to each task, which, while…

Efficient prediction of default risk for bond-issuing enterprises is pivotal for maintaining stability and fostering growth in the bond market. Conventional methods usually rely solely on an enterprise's internal data for risk assessment.…

CDR (Cross-Domain Recommendation), i.e., leveraging information from multiple domains, is a critical solution to data sparsity problem in recommendation system. The majority of previous research either focused on single-target CDR (STCDR)…

Heterogeneous graph neural network has unleashed great potential on graph representation learning and shown superior performance on downstream tasks such as node classification and clustering. Existing heterogeneous graph learning networks…

Multimodal medical image segmentation often faces missing modalities at inference, which induces disagreement among modality experts and makes fusion unstable, particularly on small foreground structures. We propose Consistency Learning of…